AI and machine learning · Free online course
Deep Learning with TensorFlow and Keras
Neural networks for the data a forest cannot read: images of surfaces and windows of vibration. Neurons, loss and gradient descent in plain words, Keras models, training well, data pipelines, CNNs, augmentation and transfer learning, sequence models, evaluation and explanation, and deployment to TensorFlow Lite — all on Colab's free GPU.
- 13 modules
- 21h 42m of video
- Intermediate
- English
- ₹0, free
- Lab practice in your browser
₹0Free for good
Worth ₹11,999 by length and depth against classroom training. It has always been free; that is not a former price.
No card. Checkout takes a minute and gives you a receipt.
Overview
About Deep Learning with TensorFlow and Keras
Build neural networks in TensorFlow and Keras for images and sensor signals, then export to TensorFlow Lite, all on Colab.
Deep Learning with TensorFlow and Keras is a free, self-paced online course from EDWartens for engineers, developers and students applying AI to real work. It has 13 modules and 21h 42m of video lessons by codebasics, freeCodeCamp.org, Edje Electronics and others, with written notes and worked problems, a practical project with a document pack and a 15-question final assessment (pass mark 60%). Learning is free with an account; an optional certificate with a public verification code is issued when you pass. Last updated 27 September 2026.
Who it is for: Engineers, developers and students applying AI to real work
This course includes
- 21h 42m of video lessons
- 13 modules with written notes and diagrams
- One final assessment: 15 questions, pass mark 60%
- Ask-an-engineer support from practising engineers
- Lifetime access, the course does not expire
- Optional verifiable certificate when you finish
- Step 1 of 3
Learn the 13 modules
21h 42m of video lessons, written notes and a practice task per module, at your own pace.
- Step 2 of 3
Pass the final assessment
15 questions drawn from every module, pass mark 60%, 3 attempts.
- Step 3 of 3
Take the certificate, if you want it
Optional, paid once, only if you choose it. The course stays free either way.
See the certificate and its price
A look inside
From the lessons
What a neural network is, and why now
by codebasics
How it learns: gradient descent and backpropagation
by codebasics
Training well: dropout, early stopping, imbalance
by codebasics
Convolutional networks
by codebasics
Sequences: 1-D CNNs, RNNs, LSTMs and autoencoders
by codebasics
Saving, TensorFlow Lite and the edge
by codebasics
Lesson frames belong to the creators named in the Credits and are shown from YouTube.
What you learn
What you will be able to do
By the end you will be able to:
- Explain what a network learns and when to use one
- Build, train and regularise Keras models
- Feed images and signal windows through tf.data
- Train CNNs and use transfer learning on small datasets
- Evaluate a model with per-class recall and Grad-CAM
How it works
How this course works
Watch the lessons
Short video lessons, one module at a time, at your own pace.
Read the notes
Open the Reading tab for the written notes and diagrams of the module.
Practise in the 3D labOptional
Try the module in the free 3D lab, in your browser.
Check yourself
Answer the questions to see what stuck before you move on.
Final assessment
Pass the final once you have been through the modules.
Certificate, if you want oneOptional
Optional, with a page anyone can use to verify it.
Syllabus
Course content, module by module
In order, at whatever pace suits you. Each module ends with a practice task that builds on the last.
- Modules
- 13
- Video lessons
- 42
- Of video
- 21h 42m
- Final questions
- 15
- 01
What a neural network is, and why now
5 lessons · 2h 10m - 02
The neuron, activation and loss
3 lessons · 58m - 03
How it learns: gradient descent and backpropagation
5 lessons · 1h 58m - 04
Keras Sequential: your first model, with lab practice:
3 lessons · 8h 9m - 05
Training well: dropout, early stopping, imbalance, with lab practice:
3 lessons · 1h 9m - 06
Data pipelines: tf.data for images and windows, with lab practice:
2 lessons · 1h 0m - 07
Convolutional networks
4 lessons · 1h 8m - 08
Augmentation and transfer learning
3 lessons · 1h 10m Final assessment · 15 questions, pass mark 60%
3D lab
Practise in the 3D lab
Practise the habits a Keras model needs, on simpler models: seeing overfitting in the gap, splitting without leakage and choosing recall, precision and the threshold.
- Overfitting: tune the treeAI Workbench, about 20 minOpen in the lab (opens in a new tab): Overfitting: tune the tree
- Train and evaluate without leakageAI Workbench, about 25 minOpen in the lab (opens in a new tab): Train and evaluate without leakage
- Choose the metric and the thresholdAI Workbench, about 25 minOpen in the lab (opens in a new tab): Choose the metric and the threshold
Optional. Skip it whenever you like: it never blocks your progress or your certificate.
Project
The course project
Optional practice that ends in the kind of job the course prepares you for, with the documents that go with it.
About 7 hours
A surface-defect classifier: baseline CNN, augmentation, transfer learning, one table
You get 1,200 greyscale 128×128 surface images in four classes (ok, scratch, dent, blob). Split by file once. Train three models on Colab's free GPU. Report them on one sealed test set with per-class recall. Explain three predictions with Grad-CAM. Export a TFLite model and report its size.
- 8documents in the pack
- 8steps to follow
- Laboptional: in the 3D lab
- 6things to hand in
- 7 hof work, at your pace
Do it in the lab: 4 steps.
Sample document pack, 8 documents, filled in for the scenario
- PlanProject plan: surface-defect classifier for painted panels, paint line 4
- URSAcceptance criteria for the surface-defect classifier
- DatasheetDataset datasheet: surface-defects-128
- ProcedureTraining and export procedure
- RegisterExperiment log: every model trained and its sealed-test score
- Test reportAcceptance test record: surface-defect classifier E07 and its TFLite file
- DatasheetModel datasheet: defects_float16.tflite
- ReportModel report: how well does it work, per defect?
Read inside the course and download as a workbook. The project is optional practice, marked when you submit it; the certificate needs only the modules and the final assessment.
About 5 hours
Vibration windows: a 1-D CNN against an LSTM for bearing and imbalance faults
You get 600 windows of 256 samples at 2 kHz, labelled healthy, bearing or imbalance. Scale with the training set's statistics, and see what per-window scaling throws away. Split by window index. Train a 1-D CNN and an LSTM and compare their test confusion matrices. Then add an autoencoder anomaly score trained on healthy windows only.
- 8documents in the pack
- 7steps to follow
- Laboptional: in the 3D lab
- 5things to hand in
- 5 hof work, at your pace
Do it in the lab: 4 steps.
Sample document pack, 8 documents, filled in for the scenario
- PlanProject plan: learned fault classifier for raw-mill motor vibration
- URSRequirements for the gateway fault classifier and anomaly score
- DatasheetDataset datasheet: vibration-windows-2khz.csv
- ProcedureTraining procedure: classifiers and anomaly score
- RegisterExperiment log: classifiers and anomaly score under both scalings
- Change noticeChange notice: scale with training statistics, not per window
- Test reportAcceptance test record: 1-D CNN classifier and autoencoder backstop
- ReportReport: does a learned model on raw vibration do the job?
Read inside the course and download as a workbook. The project is optional practice, marked when you submit it; the certificate needs only the modules and the final assessment.
Tools
Software, hardware and lessons
Software
Google Colab with a free GPU runtime. TensorFlow and Keras are pre-installed.
Hardware
None. A Raspberry Pi is optional for the deployment module.
Who it is for
Intermediate. Needs the Machine Learning with Python course, or equivalent: train/test discipline, metrics, Pandas.
Video lessons by
- codebasics
- freeCodeCamp.org
- Edje Electronics
- Connor Shorten
Independent creators, credited in full under Credits.
Software you need
What to download, where from, what it costs and how to install it. Every link goes to the maker's own site, never a mirror.
Colab's free GPU runtime runs every exercise. TensorFlow and Keras are already installed there.
Required
- 01Free, GPU time not guaranteed
Google Colab
Google, in the browser
- Runs on
- Any modern web browser
- Account
- A free Google account
Colab is free to use. In the free version GPUs and TPUs are heavily restricted and not guaranteed, sessions can run for at most 12 hours, and idle sessions are stopped. Paid plans give more reliable access.
Steps
- 1.Open colab.research.google.com and sign in with your Google account.
- 2.Click New notebook (or open the notebook your course links to).
- 3.For a GPU, choose Runtime, then Change runtime type, then pick a GPU if one is offered.
- 4.Type code in a cell and press Shift and Enter to run it.
- Save a copy to your Google Drive so your changes are kept.
- Files on the runtime are deleted when the session ends. Save outputs to Drive.
Open Google Colabcolab.research.google.com
Optional
Useful, not needed to finish the course.
- 02Free
TensorFlow
Google (TensorFlow project), a Python or npm package
- Runs on
- Python 3.10 to 3.13. Ubuntu 16.04 or later; macOS 12 or later (CPU only); Windows 7 or later (CPU only); Windows 10 build 19044 or later through WSL2 for GPU.
- Account
- None needed
Free, open source under the Apache 2.0 licence.
Steps
- 1.Install a supported Python (3.10 to 3.13) and create a virtual environment.
- 2.Upgrade pip: pip install --upgrade pip
- 3.For CPU: pip install tensorflow
- 4.For an NVIDIA GPU on Linux or WSL2: pip install tensorflow[and-cuda]
- 5.Test it: python -c "import tensorflow as tf; print(tf.config.list_physical_devices('GPU'))"
- TensorFlow 2.10 was the last release with GPU support on native Windows. For a GPU on Windows, install inside WSL2.
- If you have no GPU, use Google Colab to train larger models.
Official download pagetensorflow.org
Checked against each maker's own page on 27 September 2026. Trial lengths and editions change; the maker's page is the final word.
What you walk away with
Your certificate for Deep Learning with TensorFlow and Keras
Finish the course, pass the final, and this is the document with your name on it.
Verifiable by anyone
Adds to LinkedIn in one click
QR code on the certificate
Names what you can do
A permanent link
Earned, not attended
Learning is free. The certificate is optional.
Add it now and pay only when you have finished the course, or come back for it later. One-off, US$28.99, with a receipt.
Issued by Wartens Ltd (England and Wales, company no. 15262249) through the EDWartens training portal, as a Certificate of Completion for this self-paced course. Sold in India by Wartens Automation Private Limited. It is not a vendor certification, a university award or a CPD-accredited activity, and it does not certify competence on live equipment. Delivered electronically; see the refund policy.
Practise what you learn in the free 3D lab
Technical work is judged on what you can do: wiring, commissioning, finding a fault. Doing a task yourself teaches more than watching it a second time, and a lab lets you try it safely before you meet real equipment. It does not replace working on real hardware.
- Practise safely, so a mistake costs nothing.
- The lab checks your work like a site test, so you know when it is right.
- Free, in your browser, with nothing to install.
Why learn with EDWartens
What you get with this course.
- Free from the first lesson to the final assessment.
- Practice in a free 3D lab in your browser, with nothing to install.
- Video lessons with written notes and a project.
- An optional certificate that anyone can verify online.
FAQ
Common questions
Do I need a GPU?
Google Colab gives you one free; every model in the course trains in minutes on it. Set the runtime type to GPU in the first cell of each notebook.
How much maths?
You see gradient descent and backpropagation once, in twenty lines of NumPy, so you know what the framework does. After that Keras does the calculus and you do the engineering. Nothing in the assessments asks for derivatives.
What are the projects in the Deep Learning with TensorFlow and Keras course?
There are two projects. The first is a surface-defect classifier on 1,200 images. You compare a baseline CNN, augmentation and transfer learning on one sealed test set. You use per-class recall and Grad-CAM, and export to TensorFlow Lite. The second is a vibration-window classifier comparing a 1-D CNN with an LSTM. It adds an autoencoder anomaly score trained on healthy data only.
Should I do this before or after the OpenCV course?
After, ideally: the OpenCV course teaches you what a convolution filter is by making you tune one by hand, and it shows when classical vision is enough. This course is for when it is not.
Is the Deep Learning with TensorFlow and Keras course really free?
Yes. Every module, practice task, project and assessment. You create an account so your progress is saved and the assessments can be marked. The certificate is the only paid item, and only if you want it.
What certificate does the Deep Learning with TensorFlow and Keras course give?
An EDWartens Certificate of Completion, issued when you have finished the modules and passed the final assessment (the project is optional practice), with a verification code anyone can check. It is not a vendor credential and is never described as one.
Who made the video lessons in the Deep Learning with TensorFlow and Keras course?
The creators named in the Credits block at the foot of this page, on their own YouTube channels. EDWartens did not make the videos and the creators are not affiliated with EDWartens. What EDWartens wrote is the study plan, the notes, the practice tasks, the projects and the assessments.
Do I have to use the lab?
No. The lab is optional practice. You can skip it whenever you like, and it never blocks your progress, the final assessment or your certificate.
Is the lab free?
Yes. Every lab level for this course opens in your browser, free, with nothing to install.
Is the Deep Learning with TensorFlow and Keras course free in India, and what does the certificate cost?
Yes. Learning costs ₹0 in India: every module, the written notes, the practice tasks and the final assessment, with no card and no trial period. The only paid item is the optional EDWartens Certificate of Completion, ₹599 including GST for this intermediate course, paid in rupees through Razorpay, and only if you want it after passing the final assessment.
All course factsHide course facts
- Price
- ₹0, free for good. No trial, no card. Comparable classroom training of this length costs about ₹11,999.
- Who it is for
- Engineers, developers and students applying AI to real work
- Format
- 13 self-paced modules, 21h 42m of video, written notes, a practice task per module and one final assessment.
- Level
- Intermediate. Intermediate. Needs the Machine Learning with Python course, or equivalent: train/test discipline, metrics, Pandas.
- Brand
- Vendor-neutral
- Software
- Google Colab with a free GPU runtime. TensorFlow and Keras are pre-installed.
- Hardware
- None. A Raspberry Pi is optional for the deployment module.
- Certificate
- Optional EDWartens Certificate of Completion, ₹599 inclusive of GST for learners in India, verifiable by code. Not a vendor credential.
- Video lessons by
- codebasics, freeCodeCamp.org, Edje Electronics, Connor Shorten (independent creators, credited below)
- Language
- English
- Last updated
- 27 September 2026
Pairs well with
PLC programming · FreeSiemens TIA Portal
PLC programming · FreeSiemens TIA Portal in Three Hours
PLC programming · FreeTIA Portal: Build a Machine
Instrumentation · FreeInstrumentation for PLC EngineersMore free courses: Free AI courses for engineers
Learning paths with this course
- Applied AI engineer · 4 courses
Classroom course, Bangalore
PLC training in Bangalore
The Automation Engineer Program (AEP) is our classroom course in PLC programming and industrial automation, taught in person at our Electronic City centre.
Credits
Who made the video lessons
The video lessons in this course were created by the people below, not by EDWartens. Every lesson streams from its creator's own YouTube channel; EDWartens neither hosts nor sells that footage, and the creators are not affiliated with EDWartens and do not endorse this course. What EDWartens wrote is the study plan, the notes, the practice tasks and the assessments.
- codebasicsthe Deep Learning with TensorFlow 2.0, Keras and Python series
- freeCodeCamp.orgthe TensorFlow 2.0 complete course and the deep-learning crash course
- Edje Electronicsrunning TensorFlow Lite on a Raspberry Pi
- Connor Shortena lesson in "Evaluating and explaining a deep model"
If you are one of these creators and would like a lesson removed or credited differently, write to info@wartens.com.